Abstract
Text categorization is the main issue which affects search results. Moreover, most approaches suffer from the high dimensionality of feature space. To overcome this problem, the use of feature selection techniques with statistical text categorization is investigated. The methods were evaluated based on Chi-Square, Information Gain and Gain Ratio. The data used to test the system consisted of 1,510 documents from 2009-2010, word segmentation algorithm to key-phrase 4,408 attributes and single word 2,184 attributes. Classification techniques applied Decision Tree (ID3), Naïve Bayes (NB), Support Vector Machine (SVM) and k-nearest neighbor (KNN). Results showed that the Support Vector Machine was found to be the best technique with accuracy of a single word at 84% and key-phrase at 74% based on feature selection with Chi-Square, Information Gain and Gain Ratio with F-measure. In future research, application of text to the semantic system should be investigated further.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have